Computer Vision - ECCV 2008

1. Front Matter

   PDF

2. Lecture by Prof. Jan Koenderink

   1. Something Old, Something New, Something Borrowed, Something Blue

      • Jan J. Koenderink

      Pages 1-1

3. Recognition

   1. Learning to Localize Objects with Structured Output Regression

      • Matthew B. Blaschko, Christoph H. Lampert

      Pages 2-15

   2. Beyond Nouns: Exploiting Prepositions and Comparative Adjectives for Learning Visual Classifiers

      • Abhinav Gupta, Larry S. Davis

      Pages 16-29

   3. Learning Spatial Context: Using Stuff to Find Things

      • Geremy Heitz, Daphne Koller

      Pages 30-43

   4. Segmentation and Recognition Using Structure from Motion Point Clouds

      • Gabriel J. Brostow, Jamie Shotton, Julien Fauqueur, Roberto Cipolla

      Pages 44-57

4. Poster Session I

   1. Keypoint Signatures for Fast Learning and Recognition

      • Michael Calonder, Vincent Lepetit, Pascal Fua

      Pages 58-71

   2. Active Matching

      • Margarita Chli, Andrew J. Davison

      Pages 72-85

   3. Towards Scalable Dataset Construction: An Active Learning Approach

      • Brendan Collins, Jia Deng, Kai Li, Li Fei-Fei

      Pages 86-98

   4. GeoS: Geodesic Image Segmentation

      • Antonio Criminisi, Toby Sharp, Andrew Blake

      Pages 99-112

   5. Simultaneous Motion Detection and Background Reconstruction with a Mixed-State Conditional Markov Random Field

      • Tomás Crivelli, Gwenaelle Piriou, Patrick Bouthemy, Bruno Cernuschi-Frías, Jian-feng Yao

      Pages 113-126

   6. Semidefinite Programming Heuristics for Surface Reconstruction Ambiguities

      • Ady Ecker, Allan D. Jepson, Kiriakos N. Kutulakos

      Pages 127-140

   7. Robust Optimal Pose Estimation

      • Olof Enqvist, Fredrik Kahl

      Pages 141-153

   8. Learning to Recognize Activities from the Wrong View Point

      • Ali Farhadi, Mostafa Kamali Tabrizi

      Pages 154-166

   9. Joint Parametric and Non-parametric Curve Evolution for Medical Image Segmentation

      • Mahshid Farzinfar, Zhong Xue, Eam Khwang Teoh

      Pages 167-178

   10. Localizing Objects with Smart Dictionaries

       • Brian Fulkerson, Andrea Vedaldi, Stefano Soatto

       Pages 179-192

   11. Weakly Supervised Object Localization with Stable Segmentations

       • Carolina Galleguillos, Boris Babenko, Andrew Rabinovich, Serge Belongie

       Pages 193-207

   12. A Perceptual Comparison of Distance Measures for Color Constancy Algorithms

       • Arjan Gijsenij, Theo Gevers, Marcel P. Lucassen

       Pages 208-221

   13. Scale Invariant Action Recognition Using Compound Features Mined from Dense Spatio-temporal Corners

       • Andrew Gilbert, John Illingworth, Richard Bowden

       Pages 222-233

   14. Semi-supervised On-Line Boosting for Robust Tracking

       • Helmut Grabner, Christian Leistner, Horst Bischof

       Pages 234-247

Welcome to the 2008EuropeanConference onComputer Vision. These proce- ings are the result of a great deal of hard work by many people. To produce them, a total of 871 papers were reviewed. Forty were selected for oral pres- tation and 203 were selected for poster presentation, yielding acceptance rates of 4.6% for oral, 23.3% for poster, and 27.9% in total. Weappliedthreeprinciples.First,sincewehadastronggroupofAreaChairs, the ?nal decisions to accept or reject a paper rested with the Area Chair, who wouldbeinformedbyreviewsandcouldactonlyinconsensuswithanotherArea Chair. Second, we felt that authors were entitled to a summary that explained how the Area Chair reached a decision for a paper. Third, we were very careful to avoid con?icts of interest. Each paper was assigned to an Area Chair by the Program Chairs, and each Area Chair received a pool of about 25 papers. The Area Chairs then identi?ed and rankedappropriatereviewersfor eachpaper in their pool, and a constrained optimizationallocated three reviewers to each paper. We are very proud that every paper received at least three reviews. At this point, authors were able to respond to reviews. The Area Chairs then needed to reach a decision. We used a series of procedures to ensure careful review and to avoid con?icts of interest. ProgramChairs did not submit papers. The Area Chairs were divided into three groups so that no Area Chair in the group was in con?ict with any paper assigned to any Area Chair in the group.

• action recognition
• aerial imagery
• algorithms
• edge detection
• motion capture
• multi body tracking
• multi-modal sensors
• photography
• radiance
• segmentation
• stereo matching
• supervised learning
• surface matching
• surface reconstruction
• visually impaired

• Computer Science Department, University of Illinois at Urbana Champaign, Urbana, USA

  David Forsyth

• Department of Computing, Oxford Brookes University, Wheatley, Oxford, UK

  Philip Torr

• Department of Engineering Science, University of Oxford, Oxford, UK

  Andrew Zisserman

Policies and ethics